[llvm] [AMDGPU][True16][MC] true16 for v_fma_f16 (PR #119477)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 11 08:38:59 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mc
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
Support true16 format for v_fma_f16 in MC.
Since we are replacing v_fma_f16 to v_fma_f16_t16/v_fma_f16_fake16 in Post-GFX11, have to update the CodeGen pattern for v_fma_f16_fake16 to get CodeGen test passing. There is no pattern modified/created, but just replacing the v_fma_f16 with fake16 format.
---
Patch is 172.45 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/119477.diff
17 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIFoldOperands.cpp (+1-1)
- (modified) llvm/lib/Target/AMDGPU/SIInstrInfo.cpp (+10-8)
- (modified) llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp (+4-1)
- (modified) llvm/lib/Target/AMDGPU/VOP3Instructions.td (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir (+4-4)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3.s (+68-32)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s (+89-38)
- (modified) llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp8.s (+82-34)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3.s (+42-30)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp16.s (+57-42)
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_vop3_dpp8.s (+53-38)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3.txt (+88-16)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp16.txt (+98-14)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx11_dasm_vop3_dpp8.txt (+98-14)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3.txt (+84-15)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp16.txt (+90-15)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_vop3_dpp8.txt (+94-16)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index 4fb5cb066be7c3..c2199fd587bea6 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -199,7 +199,7 @@ static unsigned macToMad(unsigned Opc) {
case AMDGPU::V_FMAC_F16_e64:
return AMDGPU::V_FMA_F16_gfx9_e64;
case AMDGPU::V_FMAC_F16_fake16_e64:
- return AMDGPU::V_FMA_F16_gfx9_e64;
+ return AMDGPU::V_FMA_F16_gfx9_fake16_e64;
case AMDGPU::V_FMAC_LEGACY_F32_e64:
return AMDGPU::V_FMA_LEGACY_F32_e64;
case AMDGPU::V_FMAC_F64_e64:
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 4a94d690297949..22e96b780ed21f 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -4033,14 +4033,15 @@ MachineInstr *SIInstrInfo::convertToThreeAddress(MachineInstr &MI,
if (Src0Literal && !ST.hasVOP3Literal())
return nullptr;
- unsigned NewOpc = IsFMA ? IsF16 ? AMDGPU::V_FMA_F16_gfx9_e64
- : IsF64 ? AMDGPU::V_FMA_F64_e64
- : IsLegacy
- ? AMDGPU::V_FMA_LEGACY_F32_e64
- : AMDGPU::V_FMA_F32_e64
- : IsF16 ? AMDGPU::V_MAD_F16_e64
- : IsLegacy ? AMDGPU::V_MAD_LEGACY_F32_e64
- : AMDGPU::V_MAD_F32_e64;
+ unsigned NewOpc = IsFMA ? IsF16 ? ST.hasTrue16BitInsts()
+ ? AMDGPU::V_FMA_F16_gfx9_fake16_e64
+ : AMDGPU::V_FMA_F16_gfx9_e64
+ : IsF64 ? AMDGPU::V_FMA_F64_e64
+ : IsLegacy ? AMDGPU::V_FMA_LEGACY_F32_e64
+ : AMDGPU::V_FMA_F32_e64
+ : IsF16 ? AMDGPU::V_MAD_F16_e64
+ : IsLegacy ? AMDGPU::V_MAD_LEGACY_F32_e64
+ : AMDGPU::V_MAD_F32_e64;
if (pseudoToMCOpcode(NewOpc) == -1)
return nullptr;
@@ -9285,6 +9286,7 @@ static bool isRenamedInGFX9(int Opcode) {
//
case AMDGPU::V_DIV_FIXUP_F16_gfx9_e64:
case AMDGPU::V_FMA_F16_gfx9_e64:
+ case AMDGPU::V_FMA_F16_gfx9_fake16_e64:
case AMDGPU::V_INTERP_P2_F16:
case AMDGPU::V_MAD_F16_e64:
case AMDGPU::V_MAD_U16_e64:
diff --git a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
index 42df4576a774d5..979812e07fc3f7 100644
--- a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
+++ b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
@@ -455,6 +455,7 @@ void SIShrinkInstructions::shrinkMadFma(MachineInstr &MI) const {
break;
case AMDGPU::V_FMA_F16_e64:
case AMDGPU::V_FMA_F16_gfx9_e64:
+ case AMDGPU::V_FMA_F16_gfx9_fake16_e64:
NewOpcode = ST->hasTrue16BitInsts() ? AMDGPU::V_FMAAK_F16_fake16
: AMDGPU::V_FMAAK_F16;
break;
@@ -484,6 +485,7 @@ void SIShrinkInstructions::shrinkMadFma(MachineInstr &MI) const {
break;
case AMDGPU::V_FMA_F16_e64:
case AMDGPU::V_FMA_F16_gfx9_e64:
+ case AMDGPU::V_FMA_F16_gfx9_fake16_e64:
NewOpcode = ST->hasTrue16BitInsts() ? AMDGPU::V_FMAMK_F16_fake16
: AMDGPU::V_FMAMK_F16;
break;
@@ -956,7 +958,8 @@ bool SIShrinkInstructions::run(MachineFunction &MF) {
MI.getOpcode() == AMDGPU::V_FMA_F32_e64 ||
MI.getOpcode() == AMDGPU::V_MAD_F16_e64 ||
MI.getOpcode() == AMDGPU::V_FMA_F16_e64 ||
- MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_e64) {
+ MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_e64 ||
+ MI.getOpcode() == AMDGPU::V_FMA_F16_gfx9_fake16_e64) {
shrinkMadFma(MI);
continue;
}
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 8a9f8aa3d16d3a..807b6a49e8e8f0 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -341,7 +341,7 @@ let FPDPRounding = 1 in {
let SubtargetPredicate = isGFX9Plus in {
defm V_DIV_FIXUP_F16_gfx9 : VOP3Inst <"v_div_fixup_f16_gfx9",
VOP3_Profile<VOP_F16_F16_F16_F16, VOP3_OPSEL>, AMDGPUdiv_fixup>;
- defm V_FMA_F16_gfx9 : VOP3Inst <"v_fma_f16_gfx9", VOP3_Profile<VOP_F16_F16_F16_F16, VOP3_OPSEL>, any_fma>;
+ defm V_FMA_F16_gfx9 : VOP3Inst_t16 <"v_fma_f16_gfx9", VOP_F16_F16_F16_F16, any_fma>;
} // End SubtargetPredicate = isGFX9Plus
} // End FPDPRounding = 1
@@ -1706,7 +1706,7 @@ defm V_PERM_B32 : VOP3_Realtriple_gfx11_gfx12<0x244>;
defm V_XAD_U32 : VOP3_Realtriple_gfx11_gfx12<0x245>;
defm V_LSHL_ADD_U32 : VOP3_Realtriple_gfx11_gfx12<0x246>;
defm V_ADD_LSHL_U32 : VOP3_Realtriple_gfx11_gfx12<0x247>;
-defm V_FMA_F16 : VOP3_Realtriple_with_name_gfx11_gfx12<0x248, "V_FMA_F16_gfx9", "v_fma_f16">;
+defm V_FMA_F16 : VOP3_Realtriple_t16_and_fake16_gfx11_gfx12<0x248, "v_fma_f16", "V_FMA_F16_gfx9">;
defm V_MIN3_F16 : VOP3_Realtriple_gfx11<0x249>;
defm V_MIN3_I16 : VOP3_Realtriple_gfx11_gfx12<0x24a>;
defm V_MIN3_U16 : VOP3_Realtriple_gfx11_gfx12<0x24b>;
diff --git a/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir b/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir
index cefd24032871f4..85c65778933964 100644
--- a/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir
+++ b/llvm/test/CodeGen/AMDGPU/gfx11-twoaddr-fma.mir
@@ -18,7 +18,7 @@ body: |
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0
; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec
- ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, killed [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
+ ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, killed [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
%0 = IMPLICIT_DEF
%1 = COPY %0.sub1
%2 = COPY %0.sub0
@@ -43,7 +43,7 @@ body: |
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0
; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec
- ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, [[COPY1]], 0, killed [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
+ ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, [[COPY1]], 0, killed [[V_MOV_B32_e32_]], 0, killed [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
%0 = IMPLICIT_DEF
%1 = COPY %0.sub1
%2 = COPY %0.sub0
@@ -68,7 +68,7 @@ body: |
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub0
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY [[DEF]].sub1
; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1078523331, implicit $exec
- ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, killed [[COPY]], 0, [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec
+ ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, killed [[COPY]], 0, [[COPY1]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec
%0 = IMPLICIT_DEF
%1 = COPY %0.sub0
%2 = COPY %0.sub1
@@ -90,7 +90,7 @@ body: |
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY killed $vgpr0
; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 49664, implicit $exec
- ; GFX11-NEXT: [[V_FMA_F16_gfx9_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_e64 0, 16384, 0, killed [[COPY]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec
+ ; GFX11-NEXT: [[V_FMA_F16_gfx9_fake16_e64_:%[0-9]+]]:vgpr_32 = V_FMA_F16_gfx9_fake16_e64 0, 16384, 0, killed [[COPY]], 0, [[V_MOV_B32_e32_]], 0, 0, 0, implicit $mode, implicit $exec
; GFX11-NEXT: S_ENDPGM 0
%0:vgpr_32 = COPY killed $vgpr0
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
index b649bab532f262..b796d51a1f0d73 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3.s
@@ -2174,53 +2174,89 @@ v_fma_dx9_zero_f32 v5, -src_scc, |vcc_lo|, -1 mul:4
v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2
// GFX11: v_fma_dx9_zero_f32 v255, -|0xaf123456|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x09,0xd6,0xff,0xd6,0xf0,0x79,0x56,0x34,0x12,0xaf]
-v_fma_f16 v5, v1, v2, s3
-// GFX11: v_fma_f16 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00]
+v_fma_f16 v5.l, v1.l, v2.l, s3
+// GFX11: v_fma_f16 v5.l, v1.l, v2.l, s3 ; encoding: [0x05,0x00,0x48,0xd6,0x01,0x05,0x0e,0x00]
-v_fma_f16 v5, v255, s2, s105
-// GFX11: v_fma_f16 v5, v255, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01]
+v_fma_f16 v5.l, v255.l, s2, s105
+// GFX11: v_fma_f16 v5.l, v255.l, s2, s105 ; encoding: [0x05,0x00,0x48,0xd6,0xff,0x05,0xa4,0x01]
-v_fma_f16 v5, s1, v255, exec_hi
-// GFX11: v_fma_f16 v5, s1, v255, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01]
+v_fma_f16 v5.l, s1, v255.l, exec_hi
+// GFX11: v_fma_f16 v5.l, s1, v255.l, exec_hi ; encoding: [0x05,0x00,0x48,0xd6,0x01,0xfe,0xff,0x01]
-v_fma_f16 v5, s105, s105, exec_lo
-// GFX11: v_fma_f16 v5, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01]
+v_fma_f16 v5.l, s105, s105, exec_lo
+// GFX11: v_fma_f16 v5.l, s105, s105, exec_lo ; encoding: [0x05,0x00,0x48,0xd6,0x69,0xd2,0xf8,0x01]
-v_fma_f16 v5, vcc_lo, ttmp15, v3
-// GFX11: v_fma_f16 v5, vcc_lo, ttmp15, v3 ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04]
+v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l
+// GFX11: v_fma_f16 v5.l, vcc_lo, ttmp15, v3.l ; encoding: [0x05,0x00,0x48,0xd6,0x6a,0xf6,0x0c,0x04]
-v_fma_f16 v5, vcc_hi, 0xfe0b, v255
-// GFX11: v_fma_f16 v5, vcc_hi, 0xfe0b, v255 ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00]
+v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l
+// GFX11: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.l ; encoding: [0x05,0x00,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00]
-v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15|
-// GFX11: v_fma_f16 v5, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1]
+v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15|
+// GFX11: v_fma_f16 v5.l, -|ttmp15|, -|src_scc|, -|ttmp15| ; encoding: [0x05,0x07,0x48,0xd6,0x7b,0xfa,0xed,0xe1]
-v_fma_f16 v5, m0, 0.5, m0
-// GFX11: v_fma_f16 v5, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01]
+v_fma_f16 v5.l, m0, 0.5, m0
+// GFX11: v_fma_f16 v5.l, m0, 0.5, m0 ; encoding: [0x05,0x00,0x48,0xd6,0x7d,0xe0,0xf5,0x01]
-v_fma_f16 v5, |exec_lo|, -1, vcc_hi
-// GFX11: v_fma_f16 v5, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01]
+v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi
+// GFX11: v_fma_f16 v5.l, |exec_lo|, -1, vcc_hi ; encoding: [0x05,0x01,0x48,0xd6,0x7e,0x82,0xad,0x01]
-v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1]
-// GFX11: v_fma_f16 v5, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1]
+v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1]
+// GFX11: v_fma_f16 v5.h, -|exec_hi|, null, -|vcc_lo| op_sel:[1,1,1,1] ; encoding: [0x05,0x7d,0x48,0xd6,0x7f,0xf8,0xa8,0xa1]
-v_fma_f16 v5, null, exec_lo, -|0xfe0b| op_sel:[0,0,0,0]
-// GFX11: v_fma_f16 v5, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00]
+v_fma_f16 v5.l, null, exec_lo, -|0xfe0b|
+// GFX11: v_fma_f16 v5.l, null, exec_lo, -|0xfe0b| ; encoding: [0x05,0x04,0x48,0xd6,0x7c,0xfc,0xfc,0x83,0x0b,0xfe,0x00,0x00]
-v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0]
-// GFX11: v_fma_f16 v5, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3]
+v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0]
+// GFX11: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| op_sel:[1,0,0,0] ; encoding: [0x05,0x0e,0x48,0xd6,0xc1,0xfe,0xf4,0xc3]
-v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0]
-// GFX11: v_fma_f16 v5, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43]
+v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0]
+// GFX11: v_fma_f16 v5.l, 0.5, -m0, 0.5 op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0xf0,0xfa,0xc0,0x43]
-v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0]
-// GFX11: v_fma_f16 v5, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23]
+v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0]
+// GFX11: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 op_sel:[0,0,1,0] ; encoding: [0x05,0x22,0x48,0xd6,0xfd,0xd4,0x04,0x23]
-v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp
-// GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00]
+v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null clamp
+// GFX11: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00]
-v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2
-// GFX11: v_fma_f16 v255, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00]
+v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2
+// GFX11: v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null op_sel:[0,0,0,1] clamp div:2 ; encoding: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00]
+
+v_fma_f16 v5.l, v255.h, s2, s105
+// GFX11: v_fma_f16 v5.l, v255.h, s2, s105 op_sel:[1,0,0,0] ; encoding: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01]
+
+v_fma_f16 v5.l, s1, v255.h, exec_hi
+// GFX11: v_fma_f16 v5.l, s1, v255.h, exec_hi op_sel:[0,1,0,0] ; encoding: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01]
+
+v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h
+// GFX11: v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h op_sel:[0,0,1,0] ; encoding: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00]
+
+v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo|
+// GFX11: v_fma_f16 v5.l, -|exec_hi|, null, -|vcc_lo| ; encoding: [0x05,0x05,0x48,0xd6,0x7f,0xf8,0xa8,0xa1]
+
+v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc|
+// GFX11: v_fma_f16 v5.l, -1, -|exec_hi|, -|src_scc| ; encoding: [0x05,0x06,0x48,0xd6,0xc1,0xfe,0xf4,0xc3]
+
+v_fma_f16 v5.l, 0.5, -m0, 0.5
+// GFX11: v_fma_f16 v5.l, 0.5, -m0, 0.5 ; encoding: [0x05,0x00,0x48,0xd6,0xf0,0xfa,0xc0,0x43]
+
+v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1
+// GFX11: v_fma_f16 v5.l, -src_scc, |vcc_lo|, -1 ; encoding: [0x05,0x02,0x48,0xd6,0xfd,0xd4,0x04,0x23]
+
+v_fma_f16 v255.l, -|0xfe0b|, -|vcc_hi|, null clamp div:2
+// GFX11: v_fma_f16 v255.l, -|0xfe0b|, -|vcc_hi|, null clamp div:2 ; encoding: [0xff,0x83,0x48,0xd6,0xff,0xd6,0xf0,0x79,0x0b,0xfe,0x00,0x00]
+
+v_fma_f16 v5.l, v255.h, s2, s105
+// GFX11: [0x05,0x08,0x48,0xd6,0xff,0x05,0xa4,0x01]
+
+v_fma_f16 v5.l, s1, v255.h, exec_hi
+// GFX11: [0x05,0x10,0x48,0xd6,0x01,0xfe,0xff,0x01]
+
+v_fma_f16 v5.l, vcc_hi, 0xfe0b, v255.h
+// GFX11: [0x05,0x20,0x48,0xd6,0x6b,0xfe,0xfd,0x07,0x0b,0xfe,0x00,0x00]
+
+v_fma_f16 v255.h, -|0xfe0b|, -|vcc_hi|, null clamp
+// GFX11: [0xff,0xc3,0x48,0xd6,0xff,0xd6,0xf0,0x61,0x0b,0xfe,0x00,0x00]
v_fma_f32 v5, v1, v2, s3
// GFX11: v_fma_f32 v5, v1, v2, s3 ; encoding: [0x05,0x00,0x13,0xd6,0x01,0x05,0x0e,0x00]
diff --git a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
index e6f868d2b40e7e..777380e890f339 100644
--- a/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
+++ b/llvm/test/MC/AMDGPU/gfx11_asm_vop3_dpp16.s
@@ -1448,47 +1448,83 @@ v_div_fixup_f16_e64_dpp v5, v1, -|v2|, -|0.5| row_xmask:0 row_mask:0x1 bank_mask
v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 bound_ctrl:0 fi:1
// GFX11: v_div_fixup_f16_e64_dpp v255, -|v255|, -|v255|, -|src_scc| clamp row_xmask:15 row_mask:0x3 bank_mask:0x0 fi:1 ; encoding: [0xff,0x87,0x54,0xd6,0xfa,0xfe,0xf7,0xe3,0xff,0x6f,0x05,0x30]
-v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0]
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x1b,0x00,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3]
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l quad_perm:[0,1,2,3] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0xe4,0x00,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v3 row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v3.l row_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0x0e,0x04,0x01,0x40,0x01,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, v255 row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, v255.l row_half_mirror row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xfe,0x07,0x01,0x41,0x01,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, s105 row_shl:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xa6,0x01,0x01,0x01,0x01,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_hi row_shl:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xae,0x01,0x01,0x0f,0x01,0xff]
-v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1
-// GFX11: v_fma_f16_e64_dpp v5, v1, v2, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1
+// GFX11: v_fma_f16_e64_dpp v5.l, v1.l, v2.l, vcc_lo row_shr:1 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x48,0xd6,0xfa,0x04,0xaa,0x01,0x01,0x11,0x01,0xff]
-v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15
-// GFX11: v_fma_f16_e64_dpp v5, |v1|, v2, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff]
+v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf
+// GFX11: v_fma_f16_e64_dpp v5.l, |v1.l|, v2.l, -ttmp15 row_shr:15 row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x01,0x48,0xd6,0xfa,0x04,0xee,0x81,0x01,0x1f,0x01,0xff]
-v_fma_f1...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/119477
More information about the llvm-commits
mailing list